Abstract
BACKGROUND: Pneumonia is the leading cause of death in young children globally and is prevalent in the Papua New Guinea highlands. We investigated clinical predictors of hypoxic pneumonia to inform local treatment guidelines in this resource-limited setting. METHODS: Between 2013 and 2020, two consecutive prospective observational studies were undertaken enrolling children 0-4 years presenting with pneumonia to health-care facilities in Goroka Town, Eastern Highlands Province. Logistic regression models were developed to identify clinical predictors of hypoxic pneumonia (oxygen saturation <90% on presentation). Model performance was compared against established criteria to identify severe pneumonia. FINDINGS: There were 2067 cases of pneumonia; hypoxaemia was detected in 36.1%. The strongest independent predictors of hypoxic pneumonia were central cyanosis on examination (adjusted odds ratio [aOR] 5.14; 95% CI 3.47-7.60), reduced breath sounds (aOR 2.92; 95% CI 2.30-3.71), and nasal flaring or grunting (aOR 2.34; 95% CI 1.62-3.38). While the model developed to predict hypoxic pneumonia outperformed established pneumonia severity criteria, it was not sensitive enough to be clinically useful at this time. INTERPRETATION: Given signs and symptoms are unable to accurately detect hypoxia, all health care facilities should be equipped with pulse oximeters. However, for the health care worker without access to pulse oximetry, consideration of central cyanosis, reduced breath sounds, nasal flaring or grunting, age-specific tachycardia, wheezing, parent-reported drowsiness, or bronchial breathing as suggestive of hypoxaemic pneumonia, and thus severe disease, may prove useful in guiding management, hospital referral and use of oxygen therapy. FUNDING: Funded by Pfizer Global and the Bill & Melinda Gates Foundation.